File size: 4,534 Bytes
4d6e8c2
 
 
 
 
 
 
 
c72c8a8
88dad2b
c48587c
4d6e8c2
a8c9010
 
3a14b2c
8ceca59
a8c9010
ca7ae72
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4d6e8c2
 
c48587c
1c33274
70f5f26
1c33274
70f5f26
4d6e8c2
 
70f5f26
 
 
 
 
4d6e8c2
8ceca59
4d6e8c2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
70f5f26
 
 
a8c9010
 
 
4d6e8c2
 
a8c9010
0de3206
 
 
ca7ae72
 
 
 
c48587c
ca7ae72
c48587c
70f5f26
 
 
 
 
4d6e8c2
 
 
 
 
 
 
 
 
 
 
 
70f5f26
4d6e8c2
 
 
 
1c33274
4d6e8c2
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
from fastapi import APIRouter
from datetime import datetime
from datasets import load_dataset
from sklearn.metrics import accuracy_score
import random

from .utils.evaluation import TextEvaluationRequest
from .utils.emissions import tracker, clean_emissions_data, get_space_info
from .utils.predict import predict 



#packages needed for inference
import pickle
import torch
import os

import nltk
from nltk.corpus import stopwords
import spacy

nltk.download('stopwords')
# Get the list of English stop words from NLTK
nltk_stop_words = stopwords.words('english')
# Load the spaCy model for English
nlp = spacy.load("en_core_web_sm")


def process_text(text):
    """
    Process text by:
    1. Lowercasing
    2. Removing punctuation and non-alphanumeric characters
    3. Removing stop words
    4. Lemmatization
    """
    # Step 1: Tokenization & Processing with spaCy
    doc = nlp(text.lower())  # Process text with spaCy

    # Step 2: Filter out stop words, non-alphanumeric characters, punctuation, and apply lemmatization
    processed_tokens = [
        re.sub(r'[^a-zA-Z0-9]', '', token.lemma_)  # Remove non-alphanumeric characters
        for token in doc 
        if token.text not in nltk_stop_words and token.text not in string.punctuation
    ]
    
    # Optional: Filter out empty strings resulting from the regex replacement
    processed_tokens = " ".join([word for word in processed_tokens if word])
    
    return processed_tokens

router = APIRouter()

DESCRIPTION = "TF-IDF + RF"
ROUTE = "/text"

@router.post(ROUTE, tags=["Text Task"], 
             description=DESCRIPTION)
async def evaluate_text(request: TextEvaluationRequest):
    """
    Evaluate text classification for climate disinformation detection.
    
    Current Model: Random Baseline
    - Makes random predictions from the label space (0-7)
    - Used as a baseline for comparison
    """
    
    # Get space info
    username, space_url = get_space_info()

    # Define the label mapping
    LABEL_MAPPING = {
        "0_not_relevant": 0,
        "1_not_happening": 1,
        "2_not_human": 2,
        "3_not_bad": 3,
        "4_solutions_harmful_unnecessary": 4,
        "5_science_unreliable": 5,
        "6_proponents_biased": 6,
        "7_fossil_fuels_needed": 7
    }

    # Load and prepare the dataset
    dataset = load_dataset(request.dataset_name)

    # Convert string labels to integers
    dataset = dataset.map(lambda x: {"label": LABEL_MAPPING[x["label"]]})

    # Split dataset
    train_test = dataset["train"].train_test_split(test_size=request.test_size, seed=request.test_seed)
    test_dataset = train_test["test"]
    
    # Start tracking emissions
    tracker.start()
    tracker.start_task("inference")

    #--------------------------------------------------------------------------------------------
    # YOUR MODEL INFERENCE CODE HERE



    # Make random predictions (placeholder for actual model inference)
    true_labels = test_dataset["label"]

    current_file_path = os.path.abspath(__file__)
    current_dir = os.path.dirname(current_file_path)

    with open(os.path.join(current_dir,"tf-idf_vectorizer.pkl"), "rb") as tfidf_file:
        tfidf_vectorizer = pickle.load(tfidf_file)
    

    # Make predictions using the loaded model
    predictions = predict(test_dataset,tfidf_vectorizer,os.path.join(current_dir,"random_forest_model.pkl"))
    predictions = [LABEL_MAPPING[label] for label in predictions]

    #--------------------------------------------------------------------------------------------
    # YOUR MODEL INFERENCE STOPS HERE
    #--------------------------------------------------------------------------------------------   

    
    # Stop tracking emissions
    emissions_data = tracker.stop_task()
    
    # Calculate accuracy
    accuracy = accuracy_score(true_labels, predictions)
    
    # Prepare results dictionary
    results = {
        "username": username,
        "space_url": space_url,
        "submission_timestamp": datetime.now().isoformat(),
        "model_description": DESCRIPTION,
        "accuracy": float(accuracy),
        "energy_consumed_wh": emissions_data.energy_consumed * 1000,
        "emissions_gco2eq": emissions_data.emissions * 1000,
        "emissions_data": clean_emissions_data(emissions_data),
        "api_route": ROUTE,
        "dataset_config": {
            "dataset_name": request.dataset_name,
            "test_size": request.test_size,
            "test_seed": request.test_seed
        }
    }
    
    return results